MCP servers › com.synthexforge.x402 › paid-agent-services

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

com.synthexforge.x402/paid-agent-services

Paid agent services settled in USDC on Base via x402. Signed, verifiable, and free to verify. — the publisher's description

4 of 5 record checks metRead-only · tools listed 2026-10-23Topic: finance-and-payments · AI-classifiedPricing: usage-based · AI-classifiedversion 1.0.0Pythonstreamable HTTP110 tools

Summary

com.synthexforge.x402/paid-agent-services is a remote MCP server listed in the official MCP registry at version 1.0.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 110 tools, 0 resources and 0 prompts.

Record checks

4 of 5 record checks met · 4 do not apply

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
not met: Repository publishes a security policy (SECURITY.md)
not applicable: Package names its licence with a standard (SPDX) identifier
not applicable: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
not applicable: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote (hosted by the publisher)
Transport: streamable HTTP
Sign-in: none needed to open a session
Repository: public
Tools: 110
Described as changing data: 24 of 110 toolsAI-classified
Mainly works on: money, payments or trading; accounts and data in outside web servicesAI-classified
Topic: finance-and-paymentsAI-classified
Pricing: usage-basedAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

24 tools are described as changing something (a2a_escrow, agent_handoff, agent_run, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 1.0.0, published 2026-10-21 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-21 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.0 (published 2026-10-21).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

110tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: money, payments or trading; accounts and data in outside web services.

24 of 110 tools are described as changing something (creating, editing, deleting, sending or running). For 4 the reading was uncertain, so no mark is shown.

api_ebook_download
“Ebook Download VALUE: The full 121-page book 'x402 — The Agent Economy' — the definitive account of building machine-native services agents pay for, in one file.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
rates_referencereads or searches
“Signed reference rates, always as-of stamped.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- basestring
- quotestring
- symbolstring
signed_research_getreads or searches
“Signed Research VALUE: Paid route: $0.50 USDC on eip155:8453 (USD).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- topicstring
social_searchon 5 other serversreads or searches
“Multi-channel social-signal search (PAID $0.02) VALUE: Paid route: $0.02 USDC on eip155:8453 (USD).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- qstring
- channelsstring
- limitstring
a2a_escrowcreates or changes datadescribed as changing data
“Turn a deal between two agents into signed, machine-checkable release terms (PAID $0.50) VALUE: Produce the release-terms document for a deal.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- payer_walletstring
- payee_walletstring
- amount_usdnumber or null
- release_conditionsarray
- deadlinestring
- arbiterstring or null
- release_rulestring
a2a_settlement
“What does agent A owe agent B, and is the evidence sufficient to settle it?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- payerobject“One side of the obligation.”
- payeeobject“One side of the obligation.”
- taskobject“The delegated task the obligation is for.”
- amount_usdnumber or null
- completion_evidencearray
- acceptancenull
reputation_lookup
“Compute a signed agent-reputation composite from an agent id and its event list.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- agentstring
- eventsarray
trusted_route_lookupreads or searches
“Compute a signed trusted-route ranking for a counterparty.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- routesarray
agent_handoffon 1 other serverdescribed as changing data
“Hand a task from one agent to another without losing the thread (PAID $0.10) VALUE: Assess a handoff of task state between two agents.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- task_idstring
- from_agentstring
- to_agentstring
- stateobject“The state being handed over.”
- acceptance_criteriaarray
- context_sha256string or null
agent_runon 3 other serversruns code or commandsdescribed as changing data
“Attested Agent Execution — bounded agent run (PAID $1.00) VALUE: One audited agent execution with a cost ledger and a signed result, so the work is reproducible and the spend is attributable.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- taskstringrequired
- contextstring
audit_evidence_packagecreates or changes datadescribed as changing data
“Signed self-contained audit evidence package with a Merkle root (PAID $4.00) VALUE: A single signed package binding artifacts, assertions and attestations for a period — what an auditor asks for, wit…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- subjectstring
- periodstring
- artifactsarray or null
- assertionsarray or null
- attestationsarray or null
- policystring
- as_ofstring
bestex_evidence
“MiFID-style best-execution attestation.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- ordernull
- fillsarray or null
- benchmarksnull
- as_ofstring

Show 88 more tools

budget_preflightreads or searches
“Budget Preflight VALUE: Whether this call fits the budget, BEFORE you spend — turns a surprise overage into a decision you can make in advance.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- agent_idstring
- action_amount_usd
- policy
bureau_auditreads or searches
“x402 Bureau — full conformance audit of any endpoint (PAID $0.25) VALUE: A full conformance audit of any target endpoint against the x402 standard, every clause, signed and dated — the check a buyer …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- urlstringrequired
bureau_receipt_checkreads or searches
“x402 Bureau — conformance-check any issuer's receipt/offer (PAID $0.05) VALUE: Independent verification that a receipt is genuine and matches the offer it claims to settle — counterparty-side proof, …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- receiptobject
- offerobject
bureau_reputationreads or searches
“x402 Bureau — reputation from signed observation history (PAID $0.10) VALUE: The Verification Bureau's standing reputation read for a subject, from its own corpus — third-party standing you cannot ma…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- subjectstringrequired
- eventsarray
compliance_checkon 12 other servers
“Compliance Check VALUE: A specific, dated compliance verdict for one described processing activity — the artifact a regulator asks for, not a policy PDF.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
9 inputs
- purposestring
- descriptionstring
- namestring
- categorystring
- providerstring
- sectorstring
- data_typesstring
- usersstring
- custom_detailsstring
containment_registercreates or changes datadescribed as changing data
“Containment Register VALUE: A registered, signed containment policy with named emergency contacts — so 'what happens if this agent goes wrong' has an answer that is already signed and enforceable.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- agent_didstring
- emergency_contact_didstring
- policy
- rulesarray
- rule_signatures
contract_term_extract
“Signed rule-based extraction of the clauses that decide money and liability (PAID $1.50) VALUE: The obligations in a contract as structured, dated data — so compliance is a query, not a re-read of fo…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- document_textstring
- document_b64string
- document_typestring
- jurisdictionstring
- as_ofstring
corpus_anchorcreates or changes datadescribed as changing data
“Dated, signed proof that a document set existed — a Merkle root, the leaves, and a real inclusion proof (PAID $2.00) VALUE: Anchor a document set.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- documentsarray
- merklestring
- notariseboolean
- anchored_atstring
counterparty_scorereads or searches
“Counterparty credit & conduct score from your own observations (PAID $0.50) VALUE: Price the risk of paying an unknown agent, endpoint or host from YOUR OWN observations — a 0-1000 credit and conduct…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- identifierstring
- observationsnull
- as_ofstring
credentials_issuecreates or changes datadescribed as changing data
“Issue a scoped, expiring, offline-verifiable capability credential (PAID $0.05) VALUE: A scoped, time-limited, signed credential — delegation with an expiry, so access does not have to be revoked by …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 1 required
- subjectstringrequired“Who the credential is for, e.g.”
- scopesarray“The scopes to grant.”
- ttl_secondsinteger“How long the credential is valid, in seconds (1..2592000).”
- policy_refstring“The policy the credential is issued under.”
- max_usesinteger“How many uses the credential is granted (1..100000).”
- issued_forstring“Who the credential was issued to, for the record.”
data_c2pa_verify
“C2Pa Verify VALUE: Whether a media file carries a valid C2PA provenance manifest — the check that separates authentic media from generated media.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- content_hashstring
- manifest
- expected_creatorstring
- expected_generatorstring
data_freshnesson 4 other servers
“Assess whether data is still fresh, undated or conflicting (PAID $0.02) VALUE: Whether a claim's source is still fresh enough for the decision you are about to make — staleness is the failure mode no…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- as_ofstring
- budget_secondsinteger
- claimsarray or null
- source_urlstring
- reference_timestring
data_signed_snapshotcreates or changes datadescribed as changing data
“Signed Snapshot VALUE: A tamper-evident snapshot of a series with its sources and fetch time — a data point you can defend later, not just cite.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- subjectstring
- seriesarray
- sourcesarray
- fetched_at
data_validatecalculates or converts
“Validate, normalise and mechanically repair a payload against a declared JSON-Schema subset.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- payload
- schema
- repairboolean
- coerceboolean
- strictboolean
- as_ofstring
decision_attestcreates or changes datadescribed as changing data
“Signed decision attestation with an assurance level and explicit unknowns (PAID $2.50) VALUE: A signed, dated, replayable attestation of a decision and the policy that produced it — the difference be…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- actorstring
- decisionstring
- policystring
- evidencearray or null
- as_ofstring
- contextobject or null
- policy_setarray or object or null
delivery_attestcreates or changes datadescribed as changing data
“Proof that a digital deliverable arrived and matched what was promised (PAID $0.10) VALUE: A paid service on the x402 rail — the result is worth the call because the same work done by hand costs more…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- deliverableobject“The deliverable as it arrived.”
- promised_sha256string or null
- recipientstring
- delivered_atstring
- acknowledged_bystring or null
- acknowledged_atstring or null
dispute_ruling
“Signed advisory dispute ruling from a deterministic rubric (PAID $2.00) VALUE: A binding ruling on a dispute from the contract, evidence and policy — so the resolution is a signed artifact, not an ar…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- case_idstring“The caller's case id.”
- claimobject“{obligation, claimed_by, against}.”
- contractobject“{artifact_requirements, required_rows?, required_window?}.”
- evidenceobject“{buyer: [...], seller: [...]}.”
- policyobject“{on_partial: 'pro_rata'}.”
edge_priorreads or searches
“Prior-test registry query: what has actually been tested on an instrument/timeframe/strategy-type before, and what the prior evidence says.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- instrumentstring or null“The instrument to look up, e.g.”
- timeframestring or null“The timeframe to look up, e.g.”
- strategy_typestring or null“The strategy type, e.g.”
- familystring or null“The strategy family, e.g.”
- free_textstring or null“A free-text description, matched on normalised token overlap against the entry's name, type, family and edge_type.”
edge_replication
“Is that track record real, or did you find it by looking?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- returnsarray or null“The return series, as a JSON list of numbers.”
- returns_csv_b64string or null“The return series as a base64-encoded CSV, one number per row.”
- frequencystring or null“'daily' or 'per_trade'.”
- trials_attemptedinteger or null“How many configurations you tried before keeping this one.”
- claimedobject or null“Optional: {sharpe, cagr, max_dd} — your stated figures.”
- strategy_shapeobject or null“Optional: {type, instrument, timeframe}.”
forensics_ingestcreates or changes datadescribed as changing data
“Seal one signed-attribution / forensics evidence record into a tamper-evident vault entry.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- actor_didstring
- actionstring
- action_hashstring
- timestamp
- policy_refstring
- metadataobject
forensics_queryreads or searches
“Bind sealed forensics-vault entries into ONE signed query receipt.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- entriesarray
- actor_didstring
attested_financial_evidence
“Assess and attest a financial statement or metrics payload into signed, reproducible evidence.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- statement
- companystring
- periodstring
finance_precisioncalculates or converts
“Exact-decimal financial calculation with its published convention (PAID $0.01) VALUE: Exact decimal arithmetic under stated conventions — financial totals that do not drift by a cent when you scale t…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- operationstring
- params
- conventions
- evaluatedAt
fund_tearsheet
“The institutional tearsheet, reproducible: every ratio re-derivable from the returns series and the published formula version (PAID $5.00) VALUE: Compute the tearsheet.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- returnsarray
- periods_per_yearnumber
- risk_freenumber
- benchmark_returnsarray or null
governance_reservecreates or changes datadescribed as changing data
“Agent Spend Governor — ATOMIC reserved lease (PAID $0.02) VALUE: A leased, expiring reservation of budget for a named intent — spend that is committed before it is spent.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 3 required
- agent_idstringrequired
- amountnumberrequired“Spend amount in USD.”
- intentstringrequired
- ttl_secondsinteger
governance_settlecreates or changes datadescribed as changing data
“Agent Spend Governor — settle a lease, idempotent (PAID $0.02) VALUE: Closing a reservation against what was actually spent — the difference between a budget and a wish.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- lease_idstringrequired
- actual_amountnumberrequired
identity_agent_attestcreates or changes datadescribed as changing data
“Bind an agent to its operator and wallet, with the evidence and an honest grade of it (PAID $1.00) VALUE: Bind an agent to its operator and its wallet.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- agent_idstring
- operatorstring
- walletstring
- chainstring
- evidencearray
- valid_fromstring
- validity_daysnumber or null
identity_control_proofcreates or changes datadescribed as changing data
“Identity Control Proof VALUE: Proof that a claimer controls an identifier, signed and dated — so an identity claim is a verification, not an assertion.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- identifierstring
- control_methodstring
- control_evidence
- claimerstring
index_x402reads or searches
“The signed Synthex Agentic-Commerce Index: a dated, rule-published mark (PAID $5.00) VALUE: The Synthex Agentic-Commerce Index — a dated, signed mark on the agentic economy itself, computed from our …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- datestring
- methodology_versionstring
- top_ninteger
- weightingstring
invoice_ocron 1 other serverreads or searches
“Invoice Ocr VALUE: Structured line items, vendor and total from an invoice image — the manual data entry an agent removes.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- filestringrequired
latency_benchmarkon 1 other serverreads or searches
“Latency benchmark of a third-party API, measured by us (PAID $0.05) VALUE: The latency percentiles of a vendor's API from our own probes — the number a performance-based selection is actually made on.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- urlstringrequired
- window_hoursinteger
- samplesinteger
licence_checkon 1 other serverreads or searches
“Licence Check VALUE: Whether a specific dataset licence permits a specific intended use in a specific jurisdiction — a legal question with a dated answer.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 2 required
- datasetstringrequired“The dataset the question is about, e.g.”
- licence_spdxstring or null“The licence under which the data is held, as an SPDX id (MIT, Apache-2.0, GPL-3.0, CC-BY-NC-4.0, proprietary-vendor-tos, ...).”
- intended_usestringrequired“What you intend to do with the data.”
- jurisdictionstring or null“The jurisdiction the use happens in, e.g.”
mandate_compliancereads or searches
“Signed compliance certificate: does this portfolio comply with this mandate (PAID $5.00) VALUE: A signed, dated compliance certificate an allocator can actually file — replaces an analyst hour on a d…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- mandatenull
- portfolionull
- observationsnull
- as_ofstring
market_calendarreads or searches
“Signed market-hours / holiday / settlement answer (PAID $0.01) VALUE: Session hours, holidays and settlement cut-offs for a venue, DST aware — so you never settle into a closed market.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- venuestring
- operationstring
- nowEpoch
- tradeDate
market_historyon 2 other serversreads or searches
“Signed bar series over an explicit range (PAID $1.00) VALUE: Historical bars for an instrument, formatted and bounded — the data a backtest needs, without hand-assembling it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- sourcestring
- instrumentstring
- timeframestring
- start
- end
- formatstring
market_history_bulkreads or searches
“Signed bulk bar series, up to 20 pairs (PAID $5.00) VALUE: The same history for many pairs in one call — the cost of a portfolio-wide study drops to a single request.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- pairsarray
- start
- end
- formatstring
market_regimeon 4 other serversreads or searches
“Is this market trending or ranging?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- seriesobject
- methodstring
- as_ofstring
market_snapshoton 14 other serversreads or searches
“Signed OHLCV snapshot from our own market-data store (PAID $0.01) VALUE: A point-in-time market snapshot for an instrument, bounded and timestamped — the 'now' you stamp a decision with.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- instrumentstring
- granularitystring
- from_ts
- to_ts
- limit
- as_of
mcp_eval_judgereads or searches
“Judge Grade VALUE: A rubric-scored judgement of a model response, signed and dated — evaluation you can re-check rather than re-argue.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- response_pair
- rubricarray
- subjectstring
mcp_threatmodel_tool_permissionreads or searches
“Tool Permission Threatmodel VALUE: A threat model of a tool manifest with per-tool permissions and runaway protection — the analysis before you grant an agent a capability.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- manifest
- ownership_proofstring
mcp_verify_uptimereads or searches
“Uptime Canary Probe VALUE: Independent uptime confirmation tied to a settled receipt — proof of service that a self-report cannot manufacture.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- service_urlstring
- checksarray
- last_confirmed_settlement_txstring
memory_geton 17 other serversreads or searches
“Return the latest signed, reproducible sealed state for a key.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- ownerstring
- keystring
memory_puton 1 other servercreates or changes datadescribed as changing data
“Persist a budget-capped state version into a signed, reproducible memory vault.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- ownerstring
- keystring
- value
nav_attestreads or searches
“Signed NAV attestation for agent treasuries: what is this book worth, as of when, computed how (PAID $10.00) VALUE: A signed NAV attestation for agent treasuries — the single document every allocator…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- as_ofstring
- currencystring
- positionsarray or null
- casharray or null
- liabilitiesarray or null
- methodologynull
output_verifyreads or searches
“Output Verify VALUE: Whether an output actually satisfies its schema, claims and staleness budget — a check the model cannot run on itself.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- subjectstring
- outputobject or array or null
- claimedobject or null
- checksarray or null
- schemaobject or null
- stalenessBudgetSecondsinteger or number or null
- accuracyobject or null
pass_purchasedescribed as changing data
“Pass Purchase VALUE: Prepaid capacity at a lower effective per-call price — the difference between renting and owning the cost.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- route_scopestring“Which routes the pass covers.”
- calls_totalinteger“How many calls the pass buys.”
- ttl_daysinteger“How many days the pass is valid for.”
pass_purchase_trialdescribed as changing data
“Buy a trial prepaid capacity pass — $0.50 for 20 calls, 7 days (PAID $0.50) VALUE: The trial tier of the same prepaid capacity — proof of the unit economics before you commit to the full pass.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
payment_deadlinereads or searches
“Will this payment settle inside my deadline?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 5 required
- railstringrequired
- networkstringrequired
- amount_usdnumberrequired
- submitted_atstringrequired
- deadlinestringrequired
payment_envelope_validatereads or searches
“Validate a captured x402 402 payment envelope (PAID $0.25) VALUE: Whether a signed payment envelope is well-formed, unexpired and for the right resource — catch a bad payment before it settles.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- envelope
- now_epoch
- resource_urlstring
policy_checkon 6 other serversreads or searches
“Deterministic policy evaluation: is this action allowed under this policy given this caller state?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- action
- policy
- caller_state
- as_ofstring
portfolio_riskon 2 other serversreads or searches
“Signed exposure report under the caller's own risk model (PAID $3.00) VALUE: Risk for a set of positions under a named model, dated — the number that decides whether a portfolio is sized right.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- positionsarray or null
- modelobject or null
- as_ofstring
preflighton 16 other serversreads or searches
“Signed preflight verdict on a counterparty BEFORE you pay them.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- targetstringrequired
- kindstring
- checksarray
pretrade_riskreads or searches
“Pre-trade risk gate: approve / reduce / reject an order against your own declared limits (PAID $0.25) VALUE: The order gate: approve, reduce or reject an order against the risk limits you declared — …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- accountnull
- positionsarray or null
- ordernull
- limitsnull
- as_ofstring
procurement_reconcilereads or searches
“Reconcile three ledgers — what was ordered, what was delivered, what was paid — with every variance naming its direction (PAID $0.50) VALUE: Reconcile the three ledgers.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- ordersarray
- deliveriesarray
- paymentsarray
- amount_tolerancenumber or null
- quantity_tolerancenumber or null
provenance_overlaydescribed as changing data
“Signed provenance for a piece of content, so a buyer can see where it came from (PAID $0.10) VALUE: Produce a signed provenance overlay for a piece of content.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- content_sha256string
- sourcesarray
- transformationsarray
- creatorstring or null
quant_monte_carloreads or searches
“What does the equity curve look like?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- trade_distributionobject
- tradesinteger
- runsinteger
- seedinteger
- as_ofstring
quant_overlapreads or searches
“Are these two strategies the same bet?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- strategiesarray
- thresholdnumber
- as_ofstring
quant_risk_of_ruinreads or searches
“Can this sizing scheme bankrupt me?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
8 inputs
- win_ratenumber or null
- avg_win_rnumber or null
- avg_loss_rnumber or null
- risk_per_trade_pctnumber or null
- capitalnumber or null
- tradesinteger or null
- seedinteger
- as_ofstring
quant_significancereads or searches
“Is this return stream distinguishable from noise?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- returnsarray
- nullstring
- trialsinteger
- benchmark_returnsarray or null
- seedinteger
- as_ofstring
quota_preflightreads or searches
“Signed quota reservation decision (PAID $0.01) VALUE: Whether a call fits a remaining quota, before you spend it — the check that stops a quota from being discovered by exhaustion.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- agentIdstring
- targetstring
- calls
- quota
- requestIdstring
readiness_attestreads or searches
“Readiness Attest VALUE: A signed readiness attestation with the evidence and policy snapshot behind it — readiness you can evidence, not assert.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- targetstring
- policy_snapshot
- readiness_evidencearray
- custodianstring
attestation_receipton 1 other servercreates or changes datadescribed as changing data
“Mint a signed typed receipt for any transaction or action.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- receipt_typestring
- txstring
- actionstring
- actorstring
- subjectstring
- metadata
signed_researchgenerates contentdescribed as changing data
“Generate a tamper-evident, signed research brief on a requested topic.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- topicstring
- depthstring
- contextstring
route_execute
“An ADVISORY execution plan for moving money — it never moves money: no keys, no signing, no broadcast (PAID $0.05) VALUE: Plan the route.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- intentobject“What the caller wants to move.”
- constraintsobject
- rail_tablearray or null
sec_extractreads or searches
“Sec Extract VALUE: Structured data extracted from a company's SEC filings — primary filings, not a data vendor's interpretation of them.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- tickerstring
security_dependency_riskreads or searches
“Dependency Risk VALUE: Risk analysis of a dependency set for a given ecosystem — supply chain exposure enumerated rather than assumed.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- dependenciesarray
- ecosystemstring
security_redteam_authorized_scanreads or searches
“Redteam Authorized Scan VALUE: An authorized adversarial scan of a target you have evidence of permission to test — the finding, with the authorization on the record.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- target_urlstring
- authorized_testsarray
- authorization_evidencearray
- scope_descriptionstring
security_threatmodelreads or searches
“Threatmodel Analyze VALUE: A threat model of a tool manifest in its deployment context — attack surface before it is exploited.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- tool_manifest
- deployment_contextstring
settlement_conditionalreads or searches
“Signed conditional-release verdict — are the release conditions met?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- deal_idstring“The caller's deal id.”
- conditionsarray“The conditions to evaluate.”
- as_ofstring or null“The evaluation instant, ISO-8601.”
settlement_receiptreads or searches
“Signed settlement-receipt verdict for a tx hash (PAID $0.01) VALUE: Independent confirmation that a transaction settled to the right payee for the right amount — proof of payment from the ledger, not…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- txHashstring
- expectedAmountAtomic
- payerstring
- payeestring
- receipt
- minConfirmations
settlement_route_advicereads or searches
“Which rail should this settlement use?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- amount_usdnumber or null
- assetstring
- urgencystring
- destinationsarray
- constraintsobject
- rail_tablearray or null
sla_breach_evidencereads or searches
“Evidence package for a vendor SLA breach (PAID $1.00) VALUE: The evidence package when a vendor misses its stated SLA: measured against claimed, with the shortfall itemised — what a dispute needs and…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- urlstringrequired
- claimed_slaobject
- window_hoursinteger
sme_screenreads or searches
“Screen an SME sale against the house LBO structure and rules (PAID $2.50) VALUE: A structured screen of an SME on turnover, EBITDA, structure and sector — the first pass over an acquisition candidate.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
10 inputs
- price_eurnumber or null“The asking price in EUR.”
- turnover_eurnumber or null“Annual turnover (revenue) in EUR.”
- ebitda_eurnumber or null“Annual EBITDA in EUR.”
- sectorstring or null“The sector, free text, e.g.”
- locationstring or null“The location, free text, e.g.”
- employeesinteger or null“Headcount.”
- seller_financing_pctnumber or null“Seller financing offered, as a percentage of price.”
- structurestring or null“The capital structure.”
- exit_multiplenumber or null“The exit EV/EBITDA multiple.”
- notesstring or null“Free text.”
spend_anomalyreads or searches
“Is this agent's spending behaving normally?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- agent_idstring
- spend_windowarray
- baselineobject“The baseline the window is judged against.”
spend_ledger_attestcreates or changes datadescribed as changing data
“Signed attestation of an agent's spend (PAID $0.50) VALUE: A signed, dated attestation of what an agent spent, for its principal — the artefact that makes an agent's spend reviewable instead of self-…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- agent_idstringrequired
- periodobject
- entriesarray
strategy_capacityreads or searches
“How much money can this strategy actually carry?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- strategynull
- capitalnull
- marketnull
- as_ofstring
strategy_verdictreads or searches
“Is this edge deployable?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- returnsarray
- periods_per_yearinteger
- benchmark_returnsarray or null
- claimed_sharpenumber or null
- trialsinteger or null
- as_ofstring
synthesis_verdict
“Fold research + quant + audit inputs into ONE signed verdict.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- subjectstring
- researcharray
- quantarray
- auditarray
task_acceptancereads or searches
“Did the work meet the spec, criterion by criterion?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- specobject“The spec the work is judged against.”
- observedobject
uptime_attestreads or searches
“Signed uptime of a third-party API, measured by us (PAID $0.10) VALUE: The uptime of a vendor's API, measured by us and signed, so you are not trusting their own status page when you make a procureme…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- urlstringrequired
- window_hoursinteger
utils_code_review_brief
“Utils Code Review Brief VALUE: A structured review brief for a code block — the issues worth reading, separated from the noise.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- codestring
- languagestring
utils_doc_convertcalculates or converts
“Utils Doc Convert VALUE: Converting a document between formats with a signed output — turning a file into something a machine can read.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- textstring
- tostring
utils_invoice_extractcalculates or converts
“Utils Invoice Extract VALUE: Structured line items from invoice text — the manual data entry an agent removes, without the image.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- textstring
utils_pii_redactcalculates or converts
“Utils Pii Redact VALUE: Redacting names and other identifiers from text, in place — compliance with a diff you can inspect.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- textstring
- redact_namesboolean
utils_schema_cleanupcalculates or converts
“Utils Schema Cleanup VALUE: Cleaning a CSV or JSON payload against a schema — the messiness removed before it reaches your model.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- dataobject
- csvstring
utils_translate_doccalculates or converts
“Utils Translate Doc VALUE: Translating a document with its structure preserved — a document an agent in another language can actually use.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- textstring
- srcstring
- targetstring
verdict_agentreads or searches
“Dated signed verdict on a counterparty wallet (PAID $0.02) VALUE: Is this wallet safe to transact with right now?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- addressstringrequired
- chainstring or null
verdict_batchreads or searches
“Judge a whole portfolio in one call.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- itemsarray
- checksarray
- as_ofstring

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. The first 100 of 110 tools are listed. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 110 tools
Says what it returns: 100% of 110 tools
States limits, defaults or errors: 47% of 59 tools
Says when to use it: 94% of 17 tools
Items covered per tool: 3.5 of 4 on average

Counted from the listing

Parameters with a description: 15% of 415
Tools with a description: 100% of 110
Typical description length: 646 characters

The tool set

Counted from the listing

Tools: 110
Size of the list: about 35,727 tokens for an agent to load (characters ÷ 4)
Naming: 108 of 110 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 110 of 110 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://x402.synthexforge.com/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "paid-agent-services": {
      "url": "https://x402.synthexforge.com/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "paid-agent-services": {
      "type": "http",
      "url": "https://x402.synthexforge.com/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"paid-agent-services","type":"http","url":"https://x402.synthexforge.com/mcp"}'

Claude Code

claude mcp add --transport http paid-agent-services https://x402.synthexforge.com/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://x402.synthexforge.com/mcp --transport http

The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint x402.synthexforge.com/mcp	Session opened	matches	our test · 2026-10-23
No credential declared as required	Opened a session without any credential	matches	our test · 2026-10-23
Repository github.com/hermeschoosenone-debug/synthex-x402	Opens publicly	matches	api.github.com · 2026-10-22

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: com.synthexforge.x402
GitHub owner: a personal account (hermeschoosenone-debug)

Repository: github.com/hermeschoosenone-debug/synthex-x402
Stars: 0
Repository age: 0–30 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-22; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

4 of 5 record checks met · 4 do not apply

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: 0 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about com.synthexforge.x402/paid-agent-services

Answered from the data above

Is com.synthexforge.x402/paid-agent-services safe to install?

We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. 24 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Is com.synthexforge.x402/paid-agent-services free to use?

Its website (synthexforge.com/) describes a usage-based pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.

Does com.synthexforge.x402/paid-agent-services need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has com.synthexforge.x402/paid-agent-services been security tested?

Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security verdict is published before verification.

What can com.synthexforge.x402/paid-agent-services do?

It lists 110 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, run code or commands, generate content and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can com.synthexforge.x402/paid-agent-services change or delete data?

24 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does com.synthexforge.x402/paid-agent-services publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Where is the source code of com.synthexforge.x402/paid-agent-services?

In github.com/hermeschoosenone-debug/synthex-x402, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

io.github.mnemox-ai/tradememory-protocolalso has tools that calculates or converts, creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
uk.minia2a/minia2a-mcp-remotealso has tools that calculates or converts, creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
dev.clusteragent/cluster-mcpalso has tools that calculates or converts, creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
io.github.GordonHal/transaction-coordinatoralso has tools that calculates or converts, creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
me.agentworld/agentworld-mcpAgentWorld — Live AI Agent Economyalso has tools that calculates or converts, creates or changes data, runs code or commands, generates content, reads or searchescompare with this one
ai.intuitek.the-stall/the-stallThe Stallalso has tools that calculates or converts, creates or changes data, runs code or commands, generates content, reads or searchescompare with this one

Active servers whose topic is also “finance-and-payments” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 12

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside

Does not apply to this server · 4

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted a read-only session with the server's remote endpoint
1,211 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 110 tools, 0 resources, 0 prompts.
6,960 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

finance-and-payments

AI-classified · 2026-10-23

Pricing modelAI-classified

usage-based

read from synthexforge.com/ · 2026-10-23

“$0.01 $29.00 Per call”

Programming language

Python

api.github.com · 2026-10-23

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

prompts, resources, tools

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

does not apply

remote-only server: no package is shipped, so there is no package registry

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Integrity hash

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Signature / provenance

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Dependency advisories

does not apply

ships no package, so there are no dependencies to audit

Popularity

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Publisher signals

owner: a personal account · repository age: 0–30 days · stars: 0–9

api.github.com · 2026-10-22

Maintenance

active

api.github.com · 2026-10-22

Environment

the publisher's infrastructure

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “com.synthexforge.x402/paid-agent-services: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/com.synthexforge.x402/paid-agent-services

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/com.synthexforge.x402/paid-agent-services)](https://protocolprobe.com/mcp/servers/com.synthexforge.x402/paid-agent-services)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology